Search Results

In order to detect degradation of engine oil lubricant, bench testing along with a number of diesel-powered Ford trucks were instruments and tested. The purpose of the bench testing was primarily to determine performance aspects such as repeatability, hysteresis effects and so on. Vehicle testing was conducted by designing and installing a separate oil reservoir along with a circulation system which was mounted in the vicinity of the oil pan. An innovative oil sensor was directly installed on the reservoir which can measure five (5) independent oil parameters (viscosity, density, permittivity, conductance, temperature). In addition, the concept is capable of detecting the oil level continuously during normal engine operation. The sensing system consists of an ultrasonic transducer for the oil level detection as well as a Tuning Fork mechanical resonator for the oil condition measurement.

Substantial fuel economy improvements for light-duty automotive engines demand novel combustion strategies. Low temperature combustion (LTC) demonstrates potential for significant fuel efficiency improvement; however, control complexity is an impediment for real-world transient operation. Spark-assisted compression ignition (SACI) is an LTC strategy that applies a deflagration flame to generate sufficient energy to trigger autoignition in the remaining charge. Operating a practical engine with SACI combustion is a key modeling and control challenge. Current models are not sufficient for control-oriented work such as calibration optimization, transient control strategy development, and real-time control. This work describes the process and results of developing a fast-running control-oriented model for the autoignition phase of SACI combustion. A data-driven model is selected, specifically artificial neural networks (ANNs).

Electrochemical models of lithium ion batteries are today a standard tool in the automotive industry for activities related to the computer-aided engineering design, analysis, and optimization of energy storage systems for electrified vehicles. One of the challenges in the development or use of such models is the need of detailed information on the cell and electrode geometry or properties of the electrode and electrolyte materials, which are typically unavailable or difficult to retrieve by end-users. This forces engineers to resort to “hand-tuning” of many physical and geometrical parameters, using standard cell-level characterization tests. This paper proposes a method to provide information and data on individual electrode performance that can be used to simplify the calibration process for electrochemical models.

Driving inattention caused by drowsiness has been a significant reason for vehicle crash accidents, and there is a critical need to augment driving safety by monitoring driver drowsiness behaviors. For real-time drowsy driving awareness, we propose a vision-based driver drowsiness monitoring system (DDMS) for driver drowsiness behavior recognition and analysis. First, an infrared camera is deployed in-vehicle to capture the driver’s facial and head information in naturalistic driving scenarios, in which the driver may or may not wear glasses or sunglasses. Second, we propose and design a multi-modal features representation approach based on facial landmarks, and head pose which is retrieved in a convolutional neural network (CNN) regression model. Finally, an extreme learning machine (ELM) model is proposed to fuse the facial landmark, recognition model and pose orientation for drowsiness detection. The DDMS gives promptly warning to the driver once a drowsiness event is detected.

The advancements in automation, big data computing and high bandwidth networking has expedited the realization of Industrial Internet of Things (IIoT). IIoT has made inroads into many sectors including automotive, semiconductors, electronics, etc. Particularly, it has created numerous opportunities in the automotive manufacturing sector to realize the new aura of platform concepts such as smart material flow control. This paper provides a thought provoking application of IIoT in automotive composites body shop. By creating a digital twin for every physical part, we no longer need to adhere to the conventional manufacturing processes and layouts, thus opening up new opportunities in terms of equipment and space utilization. The century-old philosophy of the assembly line might not be the best layout for vehicle manufacturing, thus proposing a novel assembly grid layout inspired from a colony of ants working to accomplish a common goal.

The automotive industry is subject to stringent regulations in emissions and growing customer demands for better fuel consumption and vehicle performance. Engine calibration, a process that optimizes engine performance by tuning engine controls (actuators), becomes challenging nowadays due to significant increase of complexity of modern engines. The traditional sweep-based engine calibration method is no longer sustainable. To tackle the challenge, this work considers two powerful global optimization methods: genetic algorithm (GA) and Bayesian optimization for steady-state engine calibration for single speed-load point. GA is a branch of meta-heuristic methods that has shown a great potential on solving difficult problems in automotive engineering. Bayesian optimization is an efficient global optimization method that solves problems with computationally expensive testing such as hyperparameter tuning in deep neural network (DNN), engine testing, etc.

With increasingly stringent emissions regulations and concurrent requirements for enhanced engine thermal efficiency, a comprehensive characterization of the automotive gasoline fuel spray has become essential. The acquisition of accurate and repeatable spray data is even more critical when a combustion strategy such as gasoline direct injection is to be utilized. Without industry-wide standardization of testing procedures, large variablilities have been experienced in attempts to verify the claimed spray performance values for the Sauter mean diameter, Dv90, tip penetration and cone angle of many types of fuel sprays. A new SAE Recommended Practice document, J2715, has been developed by the SAE Gasoline Fuel Injection Standards Committee (GFISC) and is now available for the measurement and characterization of the fuel sprays from both gasoline direct injection and port fuel injection injectors.

This work discusses the development of SAE procedure J2747, “Hydraulic Pump Airborne Noise Bench Test”. This is a test procedure describing a standard method for measuring radiated sound power levels from hydraulic pumps of the type typically used in automotive power steering systems, though it can be extended for use with other types of pumps. This standard was developed by a committee of industry representatives from OEM's, suppliers and NVH testing firms familiar with NVH measurement requirements for automotive hydraulic pumps. Details of the test standard are discussed. The hardware configuration of the test bench and the configuration of the test article are described. Test conditions, data acquisition and post-processing specifics are also included. Contextual information regarding the reasoning and priorities applied by the development committee is provided to further explain the strengths, limitations and intended usage of the test procedure.

Globalization in the automotive industry has resulted in a tremendous competitive advantage to those companies who can internally communicate ideas and information effectively and in a timely manner. This paper discusses one such effort related to objectively testing vehicles for steering and handling characteristics by implementing standard test procedures, data acquisition hardware and analysis methods. Ford Motor Company's Vehicle Dynamics Test Section has refined a number of test procedures to the point that, with proper training, all design and development engineers can quickly acquire, analyze and share test results. Four of these procedures and output are discussed in detail.

This paper will describe the development of an in-vehicle data acquisition and analysis system. The problem facing the Vehicle Dynamics Test Section of Ford Motor Company was to replace an antiquated data recorder with a versatile in-vehicle data acquisition system capable of supporting vehicle dynamics testing and development. The following criteria for a system was developed: Quick and easy quick software and hardware setup Off-the-shelf hardware wherever possible User-friendly software Flexible Open-ended and modular design Rugged Cost effective Utilizing the above criteria a number of commercially available systems were evaluated and found to be lacking. Therefore it was decided that a system suitable for vehicle dynamics testing would have to be developed.

Brake system development and testing is spread over vehicle manufacturers, system and component suppliers. Test equipment from different sources, even resulting from different technology generations, different data analysis and report tools - comprising different and sometimes undocumented algorithms - lead to a difficult exchange and analysis of test results and, at the same time, contributes to unwanted test variability. Other studies regarding the test variability brought up that only a unified and unambiguous data format will allow a meaningful and comparative evaluation of these data and only standardization will reveal the actual reasons of test variability. The text at hand illustrates that a substantial part of test variability is caused by a misinterpretation of data and/or by the application of different algorithms.

This paper presents a methodology for designing a simple open-loop steering robot profile to simulate a double lane change maneuver for track testing of a heavy tractor/trailer combination vehicle. For track testing of vehicles in a lane change type of maneuver, a human driver is typically used with a desired path defined with visual cues such as traffic cones. Such tests have been shown to result in poor test repeatability due to natural variation in driver steering behavior. While a steering robot may be used to overcome this repeatability issue, such a robot typically implements open-loop maneuvers and cannot be guaranteed to cause the vehicle to accurately follow a pre-determined trajectory. This paper presents a method using offline simulation to design an open-loop steering maneuver resulting in a realistic approximation of a double lane change maneuver.

Race teams compete at a level where fractions of a second separate the finishers. Consequently, teams devote significant resources to gain a competitive edge. Limitations on track time and high track rental prices dictate efficiency in testing. Thus, proper use of data acquisition and computer aided engineering tools is essential. These tools can be used to quickly analyze test data and serve as the basis for recommendations for changes in chassis setup and driver technique. This project describes the further development of such a tool that can be used to analyze and diagnose the control inputs of a driver as well as diagnose the overall balance of the chassis (i.e., understeer and oversteer). This tool is an “expert system” (implemented in MATLAB) that provides an understanding of the effects of both chassis setup changes and driver steering, braking, and throttle control inputs on overall lap times.

This study compares the model efficacy of Neural Network and Vector Auto Regression. Further it also analyses the impact of predictors controlling for total industry volume. Understanding both the methodologies has their distinctive advantages and disadvantages. Our empirical findings indicate that based on the characteristics of data such as non-stationary, non-linearity and non-normality paves the way for use of machine learning algorithm relative to econometrics technique. Our results suggest that data type and its characteristics are more important in determining the methodology than the methodology itself. In industry, econometrics methodologies are widely used due to their usage simplicity and its ability to explain the relationships in simple terms.

It is desirable to find methods to increase electric vehicle (EV) driving range and reduce performance variability of Plug-in Hybrid Electric Vehicles (PHEV). One strategy to improve EV range is to increase the charge power limit of the traction battery, which allows for more brake energy recovery. This paper applies Big Data technology to investigate how increasing the charge power limit could affect EV range in real world usage with respect to driving behavior. Big Data Drive (BDD) data collected from Ford employee vehicles in Michigan was analyzed to assess the impact of regenerative braking power on EV range. My Ford Mobile (MFM) data was also leveraged to find correlation to drivers nationwide based on brake score statistics. Estimated results show incremental improvements in EV range from increased charge power levels. Subsequently, this methodology and process could be applied to make future design decisions based on the dynamic nature of driving habits.

In this work, we outline a process for traffic light detection in the context of autonomous vehicles and driver assistance technology features. For our approach, we leverage the automatic annotations from virtually generated data of road scenes. Using the automatically generated bounding boxes around the illuminated traffic lights themselves, we trained an 8-layer deep neural network, without pre-training, for classification of traffic light signals (green, amber, red). After training on virtual data, we tested the network on real world data collected from a forward facing camera on a vehicle. Our new region proposal technique uses color space conversion and contour extraction to identify candidate regions to feed to the deep neural network classifier. Depending on time of day, we convert our RGB images in order to more accurately extract the appropriate regions of interest and filter them based on color, shape and size. These candidate regions are fed to a deep neural network.

This work describes a single camera based object distance estimation system. As technology on vehicles is constantly advancing on the road to autonomy, it is critical to know the locations of objects in 3D space for safe behavior of the vehicle. Though significant progress has been made on object detection in 2D sensor space from a single camera, this work additionally estimates the distance to said object without requiring stereo vision or absolute knowledge of vehicle motion. Specifically, our proposed system is comprised of three modules: vision based ego-motion estimation, object-detection, and distance estimation. In particular, we compensate for the vehicle ego-motion by using pin-hole camera model to increase the accuracy of the object distance estimation.

While operating a vehicle in either autonomous or occupant piloted mode, an array of sensors can be used to guide the vehicle including stereo cameras. The state-of-the-art distance map estimation algorithms, e.g. stereo matching, usually detect corresponding features in stereo images, and estimate disparities to compute the distance map in a scene. However, depending on the image size, content and quality, the feature extraction process can become inaccurate, unstable and slow. In contrast, we employ deep convolutional neural networks, and propose two architectures to estimate distance maps from stereo images. The first architecture is a simple and generic network that identifies which features to extract, and how to combine them in a multi-resolution framework. The second architecture is a more specialized one that extracts local similarity information from two images, which are used for stereo feature matching, and fuses them at multiple resolutions to generate the distance map.

The development of an automatic control system for a towing dynamometer used for testing is described in this paper. The process involved the deployment of new power electronics circuit boards, a TELMA retarder, instrumentation and a human machine interface (HMI) achieved through an open source platform. The purpose of this platform is to have a low cost system that allows further function development, data acquisition and communication with other devices. This system is intended as a novel solution that will allow closed loop and automated tests integrated with PCM data for engine calibration. It is projected to be part of a flexible calibration system with direct communication to the interfaces used during development (ATI, ETAS), which will be used to achieve lean test and development schedules.

The air suspension development and application has becoming increasingly applied also in commercial vehicles, offering to the driver more dynamic comfort as well as contributing to the reduction of impact loads on highways. Through this project pursuit show the analysis and application of an air suspension system for commercial tractor vehicles application. A special focus was given to pneumatic actuation system, responsible for leveling and control of suspension′s stiffness under different conditions of usage, laden and unladen. The project was conducted starting with the vehicle dynamic performance analysis, evaluating the pneumatic suspension circuit modifications in order to obtain the vehicle dynamic behavior improvement, ensuring directional stability under different maneuvering conditions. For entire development were also used quality tools, considering the possible failure modes and effects as well as virtual simulation tools (Adams) and bench validations.